Deep learning for fully-automated nuclear pleomorphism scoring in breast cancer

Abstract

To guide the choice of treatment, every new breast cancer is assessed for aggressiveness (i.e., graded) by an experienced histopathologist. Typically, this tumor grade consists of three components, one of which is the nuclear pleomorphism score (the extent of abnormalities in the overall appearance of tumor nuclei). The degree of nuclear pleomorphism is subjectively classified from 1 to 3, where a score of 1 most closely resembles epithelial cells of normal breast epithelium and 3 shows the greatest abnormalities. Establishing numerical criteria for grading nuclear pleomorphism is challenging, and inter-observer agreement is poor. Therefore, we studied the use of deep learning to develop fully automated nuclear pleomorphism scoring in breast cancer. The reference standard used for training the algorithm consisted of the collective knowledge of an international panel of 10 pathologists on a curated set of regions of interest covering the entire spectrum of tumor morphology in breast cancer. To fully exploit the information provided by the pathologists, a first-of-its-kind deep regression model was trained to yield a continuous scoring rather than limiting the pleomorphism scoring to the standard three-tiered system. Our approach preserves the continuum of nuclear pleomorphism without necessitating a large data set with explicit annotations of tumor nuclei. Once translated to the traditional system, our approach achieves top pathologist-level performance in multiple experiments on regions of interest and whole-slide images, compared to a panel of 10 and 4 pathologists, respectively.

Differentiation and risk stratification of basal cell carcinoma with deep learning on histopathologic images and measuring nuclei and tumor microenvironment features

“…The discriminating nuclear texture features signify the uniformity or variance in nuclear texture may help distinguish between benign and malignant lesions. This is intuitive since in benign tumor, the constituted tumor cells are relatively well differentiated as a result of absence of nuclear atypia or nuclear pleomorphism 22 . Also, we checked the measurements related to nuclear morphological features and found the constituent tumor nuclei shared more spindle shape in comparison to BCC.…”

Prognostic value of deep learning based mitotic count in hormonal receptor- and HER2-positive breast cancer

“…Recently, we showed 30 that computer algorithms can be used to predict nuclear pleomorphism (a component of Nottingham grading), as a continuous score instead of using xed prede ned categories as de ned in the guidelines. Building upon this result, AI algorithms could be leveraged to predict multiple morphological features, including mitotic count and others, as a continuous value computed throughout the entire WSI.…”

Future Practices of Breast Pathology Using Digital and Computational Pathology

“…Grading of invasive carcinoma is based on the degree of nuclear atypia, tubule formation, and mitotic score, while DCIS is graded based only on nuclear atypia. Machine learning models to support grading of breast cancer have shown “pathologist-level” performance for the classification of nuclear grade 27–31 . Mercan et al 27 hypothesized grading nuclear atypia as a continuous variable instead of the traditional stepwise grading as low, intermediate, and high-grade nuclear score, and the developed model showed, on average, the highest agreement out of 10 pathologists.…”

“…Machine learning models to support grading of breast cancer have shown “pathologist-level” performance for the classification of nuclear grade 27–31 . Mercan et al 27 hypothesized grading nuclear atypia as a continuous variable instead of the traditional stepwise grading as low, intermediate, and high-grade nuclear score, and the developed model showed, on average, the highest agreement out of 10 pathologists. Other investigators have reported the development of machine learning models to support pathologists grading of breast cancer 28,32,33 .…”